Related papers: Logical Synchrony Networks: A formal model for det…
Efficient load-balancing mechanisms are critical for maximizing performance and increasing the quality of service (QoS) of data center networks (DCNs). Obtaining the optimal QoS while minimizing resource consumption remains a significant…
Early programming languages for software-defined networking (SDN) were built on top of the simple match-action paradigm offered by OpenFlow 1.0. However, emerging hardware and software switches offer much more sophisticated support for…
Prior-data fitted networks (PFNs) were recently proposed as a new paradigm for machine learning. Instead of training the network to an observed training set, a fixed model is pre-trained offline on small, simulated training sets from a…
More refined resource management and Quality of Service (QoS) provisioning is a critical goal of wireless communication technologies. In this paper, we propose a novel Business-Centric Network (BCN) aimed at enabling scalable QoS…
Modern processing networks often consist of heterogeneous servers with widely varying capabilities, and process job flows with complex structure and requirements. A major challenge in designing efficient scheduling policies in these…
Software Defined Networks (SDN) decouple the forwarding and control planes from each other. The control plane is assumed to have a global knowledge of the underlying physical and/or logical network topology so that it can monitor, abstract…
Harnessing parallelism in seemingly sequential models is a central challenge for modern machine learning. Several approaches have been proposed for evaluating sequential processes in parallel using iterative fixed-point methods, like…
Feedforward neural networks (FNNs) can be viewed as non-linear regression models, where covariates enter the model through a combination of weighted summations and non-linear functions. Although these models have some similarities to the…
An optimal control law for networked control systems with a discrete-time linear time-invariant (LTI) system as plant and networks between sensor and controller as well as between controller and actuator is proposed. This controller is…
Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids. Neural networks are widely considered to achieve improved prediction performances, supporting highly…
Differentiable Logic Gate Networks (DLGNs) are a very fast and energy-efficient alternative to conventional feed-forward networks. With learnable combinations of logical gates, DLGNs enable fast inference by hardware-friendly execution.…
This paper presents the first hardware implementation of bittide, a decentralized clock synchronization mechanism for achieving logical synchrony in distributed systems. We detail the design and implementation of an 8-node bittide network…
Software Defined Networking (SDN) is a new networking architecture which aims to provide better decoupling between network control (control plane) and data forwarding functionalities (data plane). This separation introduces several…
Hybrid light fidelity (LiFi) and wireless fidelity (WiFi) networks are a promising paradigm of heterogeneous network (HetNet), attributed to the complementary physical properties of optical spectra and radio frequency. However, the current…
We present a new family of exchangeable stochastic processes, the Functional Neural Processes (FNPs). FNPs model distributions over functions by learning a graph of dependencies on top of latent representations of the points in the given…
Prior-Fitted Networks (PFNs) amortize Bayesian prediction by meta-learning over a synthetic task prior, but their standard output is a posterior predictive distribution over noisy observations. For sequential decision-making, such as active…
This paper contributes to a development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed as Stochastic Configuration Networks (SCNs). In…
In this work we introduce Lean Point Networks (LPNs) to train deeper and more accurate point processing networks by relying on three novel point processing blocks that improve memory consumption, inference time, and accuracy: a…
The use of Ethernet switched networks usually involves best effort service. A recent effort by the IEEE 802.1/3 TSN group has sought to standardize the Ethernet data-link protocol such that it operates on a deterministic service in addition…
We study asynchronous federated learning mechanisms with nodes having potentially different computational speeds. In such an environment, each node is allowed to work on models with potential delays and contribute to updates to the central…